M5 Model Tree and Gene Expression Programming Based Modeling of Sandy Soil Water Movement under Surface Drip Irrigation - TI Journals

Abstract: Drip irrigation has a priority in selecting an appropriate irrigation method because of its potential of precisely applying water at the requested quantity and position through a field. A proper design and management of a drip irrigation system is dependent upon a better understanding of wetting patterns and water distribution in soil. This paper examines the potential of gene expression programming (GEP), which is a variant of genetic programming (GP), and M5 model tree in simulating wetting patterns of drip irrigation. First by considering 10 sandy soils of various sand percentages, soil wetting patterns for different emitter discharges and durations of irrigation have been simulated by using pore network modeling conjuncted by Richards’ equation (PNMCRE). Then using the calculated values of depth and radius of wetting pattern as target outputs, GEP and M5 model trees have been considered. Results showed that in estimation of radius and depth of wetting patterns, the M5 model tree had better agreement than GEP with results of PNMCRE model in terms of some statistical criteria. Also, laboratory experimental results in a sandy soil with emitter discharge of 4 L/h showed reasonable agreement with M5 model tree results. Finally it can be concluded on the basis of the results of this study that M5 model tree appears to be a promising technique for estimating wetting patterns of drip irrigation.

[1]  Chaiyuth Chinnarasri,et al.  Estimation of Pan Coefficient using M5 Model Tree , 2012 .

[2]  Gerard Arbat,et al.  Monitoring soil water status for micro-irrigation management versus modelling approach , 2008 .

[3]  Shaozhong Kang,et al.  Comparison of APRI and Hydrus-2D models to simulate soil water dynamics in a vineyard under alternate partial root zone drip irrigation , 2007, Plant and Soil.

[4]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[5]  Saeed Samadianfard,et al.  Gene expression programming analysis of implicit Colebrook–White equation in turbulent flow friction factor calculation , 2012 .

[6]  S. M. Hassanizadeh,et al.  Insights into the Relationships Among Capillary Pressure, Saturation, Interfacial Area and Relative Permeability Using Pore-Network Modeling , 2008 .

[7]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[8]  J. Philip,et al.  Steady Infiltration From Buried Point Sources and Spherical Cavities , 1968 .

[9]  Quanjiu Wang,et al.  Simulation of salinity distribution in the overlap zone with double-point-source drip irrigation using HYDRUS-3D. , 2012 .

[10]  Cândida Ferreira.  Gene Expression Programming in Problem Solving , 2002 .

[11]  J. Bear.  Dynamics of Fluids in Porous Media , 1975 .

[12]  Miguel A. Mariño,et al.  Infiltration from Trickle Irrigation Source , 1984 .

[13]  Michael A. Celia,et al.  Modeling support of functional relationships between capillary pressure, saturation, interfacial area and common lines , 2001 .

[14]  Thomas J. Trout,et al.  Comparison of HYDRUS-2D simulations of drip irrigation with experimental observations , 2004 .

[15]  Michael A. Celia,et al.  Recent advances in pore scale models for multiphase flow in porous media , 1995 .

[16]  Cândida Ferreira,et al.  Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence , 2014, Studies in Computational Intelligence.

[17]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[18]  L. Štravs,et al.  Development of a low-flow forecasting model using the M5 machine learning method , 2007 .

[19]  Ozgur Kisi,et al.  Evapotranspiration Modeling Using Linear Genetic Programming Technique , 2010 .

[20]  Dani Or,et al.  WATER AND SOLUTE DYNAMICS UNDER A DRIP-IRRIGATED CROP: EXPERIMENTS AND ANALYTICAL MODEL , 2000 .

[21]  J. Zhang,et al.  MODELING OF WATER FLOW AND NITRATE TRANSPORT UNDER SURFACE DRIP FERTIGATION , 2005 .

[22]  Randel Haverkamp.  Résolution de l'équation de l'infiltration de l'eau dans le sol : approches analytiques et numériques , 1983 .

[23]  Dimitri P. Solomatine,et al.  Machine learning in sedimentation modelling , 2006, Neural Networks.

[24]  Van Genuchten,et al.  A closed-form equation for predicting the hydraulic conductivity of unsaturated soils , 1980 .

[25]  Cândida Ferreira,et al.  Gene Expression Programming: A New Adaptive Algorithm for Solving Problems , 2001, Complex Syst..

[26]  Dimitri P. Solomatine,et al.  M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China , 2004 .

[27]  A. Nazemi,et al.  Parametric modeling of root length density and root water uptake in unsaturated soil , 2010 .

[28]  A. Warrick,et al.  Neuro-Drip: estimation of subsurface wetting patterns for drip irrigation using neural networks , 2010, Irrigation Science.

[29]  O. Kisi,et al.  Comparative analysis of ozone level prediction models using gene expression programming and multiple linear regression , 2013 .

[30]  T. B. S. Rajput,et al.  Simulation of soil wetting pattern with subsurface drip irrigation from line source , 2006 .

[31]  Vahid Joekar-Niasar,et al.  Non-equilibrium effects in capillarity and interfacial area in two-phase flow: dynamic pore-network modelling , 2010, Journal of Fluid Mechanics.

[32]  Matthew D. Jackson,et al.  Detailed physics, predictive capabilities and macroscopic consequences for pore-network models of multiphase flow. , 2002 .